"Logs of user or system queries" matching MCP servers:

Structured reasoning MCP server that decomposes problems into atomic steps (premise, reasoning, hypothesis, verification, conclusion) with confidence scoring, live visualization, and approval feedback.

MCP server providing virtual memory for AI context with durable SQLite storage, retrieval, and bounded prompt assembly to manage context windows.

Enables AI agents to query OpenRouter model information including prices, ELO rankings, context, and perform comparisons.

Enables querying multiple AI models simultaneously and returns all answers unmerged for the user to weigh.

Enables sophisticated reasoning workflows using graph-based representations for AI models.

Enables real-time auditing of LLM long-term memory to detect contradictions, user-introduced falsehoods, staleness, and unsourced fabrications, while providing a safe memory store with tools like recall, review, and restore.

MCP server that diagnoses ML model regressions by correlating drift reports, eval runs, and deploy logs, providing evidence-cited incident reports through a set of investigation tools.

A Model Context Protocol (MCP) server that enables structured multi-path investigations using a Tree of Thoughts approach.

Enables querying and managing AI logs through tools like listing logs, retrieving jobs, and performing AI-powered chat queries. Also provides access to gateway security reports and guardrail testing.

Provides tools for vehicle service search, mechanic matching, and booking generation as part of a multi-agent AI system for roadside assistance.

MCP server that provides OpenRouter model pricing data, enabling price lookups, trending/cheapest lists, and model searches without an API key.

Enables classification of GPU workloads as training, inference, or idle from telemetry data, with tools for one-shot classification, benchmarking, and audit log verification.

Enables agents to get fast, calibrated probabilistic answers from Jev (Typesafe AI) to yes/no, scale, or choice questions about provided material, without using a generative model.

Reads passports, ID cards and driver's licences from a photo or scan and returns the printed fields and MRZ as structured JSON. One credit ($0.01) per recognised document; nothing is charged when no document is found.

Provides local, deterministic scoring and detailed auditing of text for AI-writing patterns via two read-only tools, with no network calls or language models.

Enables agents to make calibrated decisions via six MCP tools for classification, relevance ranking, claim verification, action gating, next-step control, and model listing, using Jev's System One model without generating text.

Provides tools to retrieve the GodPrompt universal system prompt and its components (core skill, protocols, gates, anti-patterns) for AI software development, plus task classification. Designed for progressive context usage.

Predicts the outcome of Dutch court cases dismissed, partly granted, or granted using a model trained on 609,715 rulings, with the outcome leakage measured and removed: 92% of Dutch judgment texts state the outcome verbatim, 0.1% remains after the cut, giving 78.2% accuracy against a 43.7% majority baseline. The lekkage_check tool exposes that same measurement so anyone can test a datase

Enables reranking documents by relevance to a query through a Cohere-compatible API, so existing rerank code drops in with only a base_url change. Calls are pay-per-call in USDC via x402 or covered by a free daily tier, with no account, GPU, or model download needed.

Enables AI agents to perform dynamic and reflective problem-solving through a chain of thoughts, allowing them to break down complex problems, revise past thoughts, and explore logic branches before reaching a conclusion.